Commit
•
f0f0382
1
Parent(s):
8215b11
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +22 -22
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 279.87 +/- 21.91
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x786fdfa25fc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x786fdfa26050>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x786fdfa260e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x786fdfa26170>", "_build": "<function ActorCriticPolicy._build at 0x786fdfa26200>", "forward": "<function ActorCriticPolicy.forward at 0x786fdfa26290>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x786fdfa26320>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x786fdfa263b0>", "_predict": "<function ActorCriticPolicy._predict at 0x786fdfa26440>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x786fdfa264d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x786fdfa26560>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x786fdfa265f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x786fdf9c3700>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1700758068134035381, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV5QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHB8PaURnOCMAWyUS9eMAXSUR0C2f29j9XLedX2UKGgGR0BylEIMSbpeaAdL4WgIR0C2f5CudPLxdX2UKGgGR0Bxc4PNFBppaAdLzWgIR0C2f7pXhfjTdX2UKGgGR0BxjmRq46OpaAdLzWgIR0C2f84QSSNgdX2UKGgGR0BxsefnOjZdaAdLxWgIR0C2f80+HJtBdX2UKGgGR0BxRy4mTkhiaAdL0WgIR0C2f9wRTS9edX2UKGgGR0BzYW9xp+MIaAdL5GgIR0C2f+KpT/ACdX2UKGgGR0Bwt1M23rleaAdLymgIR0C2f+dvfj0ddX2UKGgGR0BvgDYsd1dPaAdL02gIR0C2gCDL4etCdX2UKGgGR0BwpXQ0GeMAaAdLwGgIR0C2gCPkvK2bdX2UKGgGR0Bw+lUQ04zaaAdL3WgIR0C2gDln/T9bdX2UKGgGR0BwP+gXdj5LaAdLz2gIR0C2gGCLyc0+dX2UKGgGR0Bw4+i9IwueaAdLy2gIR0C2gH5XEIgOdX2UKGgGR0BzCr+cYqG2aAdL72gIR0C2gJ7JOnEVdX2UKGgGR0BynYg4ffXPaAdLwmgIR0C2gK7vgFX8dX2UKGgGR0ByMvFglWwNaAdL6mgIR0C2gLcKkVN6dX2UKGgGR0BwQKLxZuAJaAdL02gIR0C2gPGZmZmadX2UKGgGR0Bxlz2K2rn1aAdL0GgIR0C2gRnaBZp0dX2UKGgGR0BxhOo2n88+aAdL1WgIR0C2gThnvlU7dX2UKGgGR0ByfZjslb/waAdL2GgIR0C2gU5id8RddX2UKGgGR0BzJi05U96kaAdL1WgIR0C2gVDLwF1TdX2UKGgGR0Byow6p5u63aAdLwmgIR0C2gW7+DOC5dX2UKGgGR0BzEZ4LThHcaAdNCwFoCEdAtoGTmNipenV9lChoBkdAcbkEd/8VHmgHS9RoCEdAtoGnZsbednV9lChoBkdAc2OE1EVnEmgHTQkBaAhHQLaBqxREWqN1fZQoaAZHQHJUjlo11nxoB0vmaAhHQLaBr3i704B1fZQoaAZHQHLKc6FM7EJoB0vMaAhHQLaBv6NEPUd1fZQoaAZHQHOM+SntOVRoB0vSaAhHQLaB41twaR91fZQoaAZHQHJc8AFPi1loB0vMaAhHQLaB+bNr0rd1fZQoaAZHQG/GUvoNd7hoB0vHaAhHQLaCCP/7zkJ1fZQoaAZHQHE+qD9OymhoB0uxaAhHQLaCG1LJ0XB1fZQoaAZHQHImxtpEhJRoB0vcaAhHQLaFqhQFcIJ1fZQoaAZHQHLyPsNUfgdoB0vAaAhHQLaF+eNDMNd1fZQoaAZHQHC3K7qY7aJoB0vYaAhHQLaGZWbwz+F1fZQoaAZHQHNTvnjhky1oB0vZaAhHQLaGhsCkoF51fZQoaAZHQHGa593KSxJoB0vxaAhHQLaGyOcDr7h1fZQoaAZHQHEk/pY9xIdoB0vhaAhHQLaG0NCZ4Od1fZQoaAZHQHMd8SXdCVtoB0vCaAhHQLaG2sFt8/l1fZQoaAZHQG8Zg8r7O3VoB0vNaAhHQLaG8sJIDo11fZQoaAZHQHMaucx0uDloB0vIaAhHQLaG9GM4tHx1fZQoaAZHQHB8IFV1fVtoB0vJaAhHQLaHDnjABT51fZQoaAZHQHMNkaya/h5oB00HAWgIR0C2h1ztPYWddX2UKGgGR0BxXR3Qla8paAdLyGgIR0C2h2AI6bONdX2UKGgGR0ByszTDwYtQaAdLvWgIR0C2h3WseXAudX2UKGgGR0BxHGuJUHY6aAdL7GgIR0C2h5ZSJj2BdX2UKGgGR0BxgXLEDQqqaAdL72gIR0C2h9C39aUzdX2UKGgGR0ByXHx+az/qaAdL4WgIR0C2h9aHbh3rdX2UKGgGR0BnDj0Fr2xqaAdN6ANoCEdAtogFuKoAGXV9lChoBkdAclKSVnmJWWgHS+poCEdAtogu8K5TZXV9lChoBkdActQL8aXKKmgHS99oCEdAtohsOoYNzHV9lChoBkdAbu8GB4D9wWgHS8doCEdAtoibTlT3qXV9lChoBkdAc2wHZsbedmgHS+hoCEdAtoidc/t6X3V9lChoBkdAcXiGe+VTrGgHS81oCEdAtoigQRPGhnV9lChoBkdAcKsVC5VfeGgHS89oCEdAtoi+2TgVGnV9lChoBkdAb6+w+MZP22gHS9NoCEdAtojGjJuEVXV9lChoBkdAco3Aeq7yx2gHS+doCEdAtojPEBKcu3V9lChoBkdAcj+aQFLWZ2gHS9BoCEdAtojXXqZ+hHV9lChoBkdAcJugAZKnN2gHS8poCEdAtokSL1mJ33V9lChoBkdAcDcLwnYxtmgHS9VoCEdAtolAYixFAnV9lChoBkdAcV9UtqYZ22gHS99oCEdAtolAgq3EynV9lChoBkdAccGXAuZkTmgHS9doCEdAtolgAxSHd3V9lChoBkdAcSEBS1mapmgHS+RoCEdAtomy2hIvrXV9lChoBkdAcT0IJZ4fOmgHS71oCEdAtom/TgEU03V9lChoBkdAcEQn3cpLEmgHS+toCEdAtonMDLbHqHV9lChoBkdAcjcM98qnWWgHS9loCEdAtonXwG4ZuXV9lChoBkdAcAqHBUJfIGgHS7loCEdAtoo3k+5e7nV9lChoBkdAdBopHI6sAGgHS9ZoCEdAtopMS26TXHV9lChoBkdAcrvQ8OkLyGgHS9ZoCEdAtoqBhH9WIXV9lChoBkdAcb5ufEn9emgHS+loCEdAtoq4+pwS8XV9lChoBkdAcVELjxTbWWgHS9xoCEdAtorh+iJwbXV9lChoBkdAcxWRU3n6mGgHS+hoCEdAtor2CL/CInV9lChoBkdAcnAQ9RrJsGgHS8hoCEdAtos1jurp7nV9lChoBkdAcFAu0CzTnmgHS8xoCEdAtotCfnOjZnV9lChoBkdAcMATx5LRKGgHS75oCEdAtotIh2W6b3V9lChoBkdAcQOgoPTXrmgHS/BoCEdAtottBqsU7HV9lChoBkdAcCDKMvRJE2gHS9VoCEdAtovsZm7J4nV9lChoBkdAcctQkona4GgHS85oCEdAtov0vRJEpnV9lChoBkdAcdvUHIIWxmgHS9toCEdAtowOGvfTC3V9lChoBkdAcXkxxDLKWGgHS9NoCEdAtox9HQQcxXV9lChoBkdAcG8pL26ClWgHS9FoCEdAtoyMWj4593V9lChoBkdAc3ox9G7SRmgHTQUBaAhHQLaMoBnBciZ1fZQoaAZHQHDhrxNIsiBoB0vcaAhHQLaM4QY1pCd1fZQoaAZHQHFwho7FKkFoB0vSaAhHQLaM9ZiNKiB1fZQoaAZHQHAqEnTiKixoB0vTaAhHQLaND2RJVbR1fZQoaAZHQHL8mpEQXhxoB0vDaAhHQLaNJXenAIp1fZQoaAZHQHM0D4L1EmZoB0vmaAhHQLaNOt/nW8R1fZQoaAZHQHJf0CvHLidoB0vSaAhHQLaNRsK9f1J1fZQoaAZHQHOYCy+pOvdoB0vbaAhHQLaNWj5sTFl1fZQoaAZHQHHa9hqj8DVoB0vcaAhHQLaNcChvitJ1fZQoaAZHQG/uf/WDpTxoB0vZaAhHQLaNuNs3yZt1fZQoaAZHQHA/65kK/mFoB0vSaAhHQLaNvqu8sc11fZQoaAZHQHFa1UIcBENoB0vwaAhHQLaN6RW912d1fZQoaAZHQG5TssYl6Z9oB0vPaAhHQLaOD+MZP2x1fZQoaAZHQHA3jKxLTQVoB0vbaAhHQLaOHmUnogV1fZQoaAZHQHOERLf1pTNoB0vVaAhHQLaOKkJ8fFJ1fZQoaAZHQG9PlIVdonNoB0u/aAhHQLaORVUuL751fZQoaAZHQHHhkNBnjABoB0vOaAhHQLaOTEc81XN1fZQoaAZHQHLat1loUSJoB0vMaAhHQLaOlBdld1N1fZQoaAZHQG6rASOBDohoB0vCaAhHQLaOux7zCk51fZQoaAZHQHL/piZv1lJoB0vaaAhHQLaOxv1DjR51ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 984, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "False", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x79f4ce3a4c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79f4ce3a4ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79f4ce3a4d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79f4ce3a4dc0>", "_build": "<function ActorCriticPolicy._build at 0x79f4ce3a4e50>", "forward": "<function ActorCriticPolicy.forward at 0x79f4ce3a4ee0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79f4ce3a4f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79f4ce3a5000>", "_predict": "<function ActorCriticPolicy._predict at 0x79f4ce3a5090>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79f4ce3a5120>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79f4ce3a51b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79f4ce3a5240>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79f4ce345780>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1700758058840678588, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 496, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "False", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9fb2ffc6cd570abebd819257a67791544a22e21d082aaeaf37862243a77dbed
|
3 |
+
size 146547
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,51 +4,51 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
-
"learning_rate": 0.
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": null,
|
33 |
"_last_episode_starts": {
|
34 |
":type:": "<class 'numpy.ndarray'>",
|
35 |
-
":serialized:": "
|
36 |
},
|
37 |
"_last_original_obs": null,
|
38 |
"_episode_num": 0,
|
39 |
"use_sde": false,
|
40 |
"sde_sample_freq": -1,
|
41 |
-
"_current_progress_remaining": -0.
|
42 |
"_stats_window_size": 100,
|
43 |
"ep_info_buffer": {
|
44 |
":type:": "<class 'collections.deque'>",
|
45 |
-
":serialized:": "
|
46 |
},
|
47 |
"ep_success_buffer": {
|
48 |
":type:": "<class 'collections.deque'>",
|
49 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
50 |
},
|
51 |
-
"_n_updates":
|
52 |
"observation_space": {
|
53 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
54 |
":serialized:": "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",
|
@@ -91,6 +91,6 @@
|
|
91 |
"target_kl": null,
|
92 |
"lr_schedule": {
|
93 |
":type:": "<class 'function'>",
|
94 |
-
":serialized:": "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
|
95 |
}
|
96 |
}
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x79f4ce3a4c10>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79f4ce3a4ca0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79f4ce3a4d30>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79f4ce3a4dc0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x79f4ce3a4e50>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x79f4ce3a4ee0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x79f4ce3a4f70>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79f4ce3a5000>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x79f4ce3a5090>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79f4ce3a5120>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79f4ce3a51b0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x79f4ce3a5240>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x79f4ce345780>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1700758058840678588,
|
30 |
+
"learning_rate": 0.001,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": null,
|
33 |
"_last_episode_starts": {
|
34 |
":type:": "<class 'numpy.ndarray'>",
|
35 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
36 |
},
|
37 |
"_last_original_obs": null,
|
38 |
"_episode_num": 0,
|
39 |
"use_sde": false,
|
40 |
"sde_sample_freq": -1,
|
41 |
+
"_current_progress_remaining": -0.015808000000000044,
|
42 |
"_stats_window_size": 100,
|
43 |
"ep_info_buffer": {
|
44 |
":type:": "<class 'collections.deque'>",
|
45 |
+
":serialized:": "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"
|
46 |
},
|
47 |
"ep_success_buffer": {
|
48 |
":type:": "<class 'collections.deque'>",
|
49 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
50 |
},
|
51 |
+
"_n_updates": 496,
|
52 |
"observation_space": {
|
53 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
54 |
":serialized:": "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",
|
|
|
91 |
"target_kl": null,
|
92 |
"lr_schedule": {
|
93 |
":type:": "<class 'function'>",
|
94 |
+
":serialized:": "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"
|
95 |
}
|
96 |
}
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87978
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66460abeeb6f2e959d74752c6cd5a29a4aea7311fee32a283cd99373cb5d1af1
|
3 |
size 87978
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43634
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d12fadf3dcfeebdd17f85bffd299c4bf92b43cf91da435bc13ceb84e4890f81
|
3 |
size 43634
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 279.8742468795158, "std_reward": 21.909221182867455, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-23T17:37:50.900544"}
|